Ivan Nikishev
inikishev
·
AI & ML interests
ML and AI
Recent Activity
new activity about 11 hours ago
Qwen/Qwen3.8-2.4T-A95B:27b when? new activity 8 days ago
roneneldan/TinyStories-1M:tool use new activity 13 days ago
ben072292/qwen3.6-35b-a3b-grpo-checkpoints:how much vram did it require to grpo qwen3.6 35b a3bOrganizations
None yet
27b when?
🚀 9
11
#1 opened about 12 hours ago
by
tigerjjw53
how much vram did it require to grpo qwen3.6 35b a3b
#1 opened 13 days ago
by
inikishev
web search
1
#22 opened 14 days ago
by
inikishev
did you train it for 90 rl steps
1
#16 opened 14 days ago
by
inikishev
謝謝你 claude 感謝開源
3
#130 opened 15 days ago
by
Tianming6233
sample rate
1
#5 opened 22 days ago
by
inikishev
can you release mtp as its own 3b model
1
#22 opened 23 days ago
by
inikishev
whats larger 1 or 2
🔥 2
1
#21 opened 29 days ago
by
inikishev
Can't load in Unsloth Studio!
2
#6 opened about 1 month ago
by
inikishev
i want a new model
👍 2
1
#266 opened about 1 month ago
by
inikishev
how to use
#1 opened about 1 month ago
by
inikishev
Can thinking be toggled per response in a multi-turn conversation?
5
#2 opened 2 months ago
by
lostmsu
please RL this model
#14 opened about 1 month ago
by
inikishev
deepreinforce-ai/Ornith-1.0-9B is better than empero-ai/Qwythos-9B-Claude-Mythos-5-1M
🔥 4
2
#10 opened about 1 month ago
by
tooltd
🚩 Report: Illegal or restricted content
3
#2 opened about 1 month ago
by
agrmbl
please give me access
#20 opened about 1 month ago
by
inikishev
New activity in Rikunarita-ORG/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive_GGUF-Q4_K_P about 1 month ago
processing
#2 opened about 1 month ago
by
inikishev